Výsledky vyhľadávania - "IEEE Conference on Computer Vision and Pattern Recognition. Proceedings"

Beyond short snippets: Deep networks for video classification Autor Ng, Joe Yue-Hei, Hausknecht, Matthew, Vijayanarasimhan, Sudheendra, Vinyals, Oriol, Monga, Rajat, Toderici, George

“…Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection,…”
Získať plný text

Deeply learned face representations are sparse, selective, and robust Autor Sun, Yi, Wang, Xiaogang, Tang, Xiaoou

“…This paper designs a high-performance deep convolutional network (DeepID2+) for face recognition. It is learned with the identification-verification…”
Získať plný text

Deep filter banks for texture recognition and segmentation Autor Cimpoi, Mircea, Maji, Subhransu, Vedaldi, Andrea

“…Research in texture recognition often concentrates on the problem of material recognition in uncluttered conditions, an assumption rarely met by applications…”
Získať plný text

DeepID-Net: Deformable deep convolutional neural networks for object detection Autor Ouyang, Wanli, Wang, Xiaogang, Zeng, Xingyu, Qiu, Shi, Luo, Ping, Tian, Yonglong, Li, Hongsheng, Yang, Shuo, Wang, Zhe, Loy, Chen-Change, Tang, Xiaoou

“…In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has…”
Získať plný text

Deformable part models are convolutional neural networks Autor Girshick, Ross, Iandola, Forrest, Darrell, Trevor, Malik, Jitendra

“…Deformable part models (DPMs) and convolutional neural networks (CNNs) are two widely used tools for visual recognition. They are typically viewed as distinct…”
Získať plný text

Filtered channel features for pedestrian detection Autor Zhang, Shanshan, Benenson, Rodrigo, Schiele, Bernt

“…This paper starts from the observation that multiple top performing pedestrian detectors can be modelled by using an intermediate layer filtering low-level…”
Získať plný text

Data-driven 3D Voxel Patterns for object category recognition Autor Yu Xiang, Wongun Choi, Yuanqing Lin, Savarese, Silvio

“…Despite the great progress achieved in recognizing objects as 2D bounding boxes in images, it is still very challenging to detect occluded objects and estimate…”
Získať plný text

100+ Times Faster Weighted Median Filter (WMF) Autor Zhang, Qi, Xu, Li, Jia, Jiaya

“…Weighted median, in the form of either solver or filter, has been employed in a wide range of computer vision solutions for its beneficial properties in…”
Získať plný text

Simultaneous video defogging and stereo reconstruction Autor Li, Zhuwen, Tan, Ping, Tan, Robby T., Zou, Danping, Zhou, Steven Zhiying, Cheong, Loong-Fah

“…We present a method to jointly estimate scene depth and recover the clear latent image from a foggy video sequence. In our formulation, the depth cues from…”
Získať plný text

Going deeper with convolutions Autor Szegedy, Christian, Wei Liu, Yangqing Jia, Sermanet, Pierre, Reed, Scott, Anguelov, Dragomir, Erhan, Dumitru, Vanhoucke, Vincent, Rabinovich, Andrew

“…We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the…”
Získať plný text

Fully convolutional networks for semantic segmentation Autor Long, Jonathan, Shelhamer, Evan, Darrell, Trevor

“…Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end,…”
Získať plný text

FaceNet: A unified embedding for face recognition and clustering Autor Schroff, Florian, Kalenichenko, Dmitry, Philbin, James

“…Despite significant recent advances in the field of face recognition [10, 14, 15, 17], implementing face verification and recognition efficiently at scale…”
Získať plný text

3D ShapeNets: A deep representation for volumetric shapes Autor Zhirong Wu, Song, Shuran, Khosla, Aditya, Fisher Yu, Linguang Zhang, Xiaoou Tang, Xiao, Jianxiong

“…3D shape is a crucial but heavily underutilized cue in today's computer vision systems, mostly due to the lack of a good generic shape representation. With the…”
Získať plný text

Show and tell: A neural image caption generator Autor Vinyals, Oriol, Toshev, Alexander, Bengio, Samy, Erhan, Dumitru

“…Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language…”
Získať plný text

CIDEr: Consensus-based image description evaluation Autor Vedantam, Ramakrishna, Zitnick, C. Lawrence, Parikh, Devi

“…Automatically describing an image with a sentence is a long-standing challenge in computer vision and natural language processing. Due to recent progress in…”
Získať plný text

Deep visual-semantic alignments for generating image descriptions Autor Karpathy, Andrej, Fei-Fei, Li

“…We present a model that generates natural language descriptions of images and their regions. Our approach leverages datasets of images and their sentence…”
Získať plný text

Long-term recurrent convolutional networks for visual recognition and description Autor Donahue, Jeff, Hendricks, Lisa Anne, Guadarrama, Sergio, Rohrbach, Marcus, Venugopalan, Subhashini, Darrell, Trevor, Saenko, Kate

“…Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or…”
Získať plný text

Deep neural networks are easily fooled: High confidence predictions for unrecognizable images Autor Anh Nguyen, Yosinski, Jason, Clune, Jeff

“…Deep neural networks (DNNs) have recently been achieving state-of-the-art performance on a variety of pattern-recognition tasks, most notably visual…”
Získať plný text

ActivityNet: A large-scale video benchmark for human activity understanding Autor Caba Heilbron, Fabian, Escorcia, Victor, Ghanem, Bernard, Niebles, Juan Carlos

“…In spite of many dataset efforts for human action recognition, current computer vision algorithms are still severely limited in terms of the variability and…”
Získať plný text

Object scene flow for autonomous vehicles Autor Menze, Moritz, Geiger, Andreas

“…This paper proposes a novel model and dataset for 3D scene flow estimation with an application to autonomous driving. Taking advantage of the fact that outdoor…”
Získať plný text